Log In Sign Up

Evolving GANs: When Contradictions Turn into Compliance

by   Sauptik Dhar, et al.

Limited availability of labeled-data makes any supervised learning problem challenging. Alternative learning settings like semi-supervised and universum learning alleviate the dependency on labeled data, but still require a large amount of unlabeled data, which may be unavailable or expensive to acquire. GAN-based synthetic data generation methods have recently shown promise by generating synthetic samples to improve task at hand. However, these samples cannot be used for other purposes. In this paper, we propose a GAN game which provides improved discriminator accuracy under limited data settings, while generating realistic synthetic data. This provides the added advantage that now the generated data can be used for other similar tasks. We provide the theoretical guarantees and empirical results in support of our approach.


page 8

page 15

page 16

page 17

page 20


How Does GAN-based Semi-supervised Learning Work?

Generative adversarial networks (GANs) have been widely used and have ac...

EC-GAN: Low-Sample Classification using Semi-Supervised Algorithms and GANs

Semi-supervised learning has been gaining attention as it allows for per...

OSSGAN: Open-Set Semi-Supervised Image Generation

We introduce a challenging training scheme of conditional GANs, called o...

Semi-Supervised Learning with GANs for Device-Free Fingerprinting Indoor Localization

Device-free wireless indoor localization is a key enabling technology fo...

Statistical Keystroke Synthesis for Improved Bot Detection

This work proposes two statistical approaches for the synthesis of keyst...

Using Synthetic Data to Enhance the Accuracy of Fingerprint-Based Localization: A Deep Learning Approach

Human-centered data collection is typically costly and implicates issues...

CR-GAN: Learning Complete Representations for Multi-view Generation

Generating multi-view images from a single-view input is an essential ye...